Eu Jeong Ku, Chaelin Lee, Jaeyoon Shim, Sihoon Lee, Kyoung-Ah Kim, Sang Wan Kim, Yumie Rhee, Hyo-Jeong Kim, Jung Soo Lim, Choon Hee Chung, Sung Wan Chun, Soon-Jib Yoo, Ohk-Hyun Ryu, Ho Chan Cho, A Ram Hong, Chang Ho Ahn, Jung Hee Kim, Man Ho Choi
Endocrinol Metab. 2021;36(5):1131-1141. Published online October 21, 2021
Background Conventional diagnostic approaches for adrenal tumors require multi-step processes, including imaging studies and dynamic hormone tests. Therefore, this study aimed to discriminate adrenal tumors from a single blood sample based on the combination of liquid chromatography-mass spectrometry (LC-MS) and machine learning algorithms in serum profiling of adrenal steroids.
Methods The LC-MS-based steroid profiling was applied to serum samples obtained from patients with nonfunctioning adenoma (NFA, n=73), Cushing’s syndrome (CS, n=30), and primary aldosteronism (PA, n=40) in a prospective multicenter study of adrenal disease. The decision tree (DT), random forest (RF), and extreme gradient boost (XGBoost) were performed to categorize the subtypes of adrenal tumors.
Results The CS group showed higher serum levels of 11-deoxycortisol than the NFA group, and increased levels of tetrahydrocortisone (THE), 20α-dihydrocortisol, and 6β-hydroxycortisol were found in the PA group. However, the CS group showed lower levels of dehydroepiandrosterone (DHEA) and its sulfate derivative (DHEA-S) than both the NFA and PA groups. Patients with PA expressed higher serum 18-hydroxycortisol and DHEA but lower THE than NFA patients. The balanced accuracies of DT, RF, and XGBoost for classifying each type were 78%, 96%, and 97%, respectively. In receiver operating characteristics (ROC) analysis for CS, XGBoost, and RF showed a significantly greater diagnostic power than the DT. However, in ROC analysis for PA, only RF exhibited better diagnostic performance than DT.
Conclusion The combination of LC-MS-based steroid profiling with machine learning algorithms could be a promising one-step diagnostic approach for the classification of adrenal tumor subtypes.
Citations
Citations to this article as recorded by
Treating Primary Aldosteronism-Induced Hypertension: Novel Approaches and Future Outlooks Nathan Mullen, James Curneen, Padraig T Donlon, Punit Prakash, Irina Bancos, Mark Gurnell, Michael C Dennedy Endocrine Reviews.2024; 45(1): 125. CrossRef
Serum and hair steroid profiles in patients with nonfunctioning pituitary adenoma undergoing surgery: A prospective observational study Seung Shin Park, Yong Hwy Kim, Ho Kang, Chang Ho Ahn, Dong Jun Byun, Man Ho Choi, Jung Hee Kim The Journal of Steroid Biochemistry and Molecular Biology.2023; 230: 106276. CrossRef
Recent Updates on the Management of Adrenal Incidentalomas Seung Shin Park, Jung Hee Kim Endocrinology and Metabolism.2023; 38(4): 373. CrossRef
LC-MS based simultaneous profiling of adrenal hormones of steroids, catecholamines, and metanephrines Jongsung Noh, Chaelin Lee, Jung Hee Kim, Seung Woon Myung, Man Ho Choi Journal of Lipid Research.2023; 64(11): 100453. CrossRef
2023 Korean Endocrine Society Consensus Guidelines for the Diagnosis and Management of Primary Aldosteronism Jeonghoon Ha, Jung Hwan Park, Kyoung Jin Kim, Jung Hee Kim, Kyong Yeun Jung, Jeongmin Lee, Jong Han Choi, Seung Hun Lee, Namki Hong, Jung Soo Lim, Byung Kwan Park, Jung-Han Kim, Kyeong Cheon Jung, Jooyoung Cho, Mi-kyung Kim, Choon Hee Chung Endocrinology and Metabolism.2023; 38(6): 597. CrossRef
Toward Systems-Level Metabolic Analysis in Endocrine Disorders and Cancer Aliya Lakhani, Da Hyun Kang, Yea Eun Kang, Junyoung O. Park Endocrinology and Metabolism.2023; 38(6): 619. CrossRef
Prevalence and Characteristics of Adrenal Tumors in an Unselected Screening Population Ying Jing, Jinbo Hu, Rong Luo, Yun Mao, Zhixiao Luo, Mingjun Zhang, Jun Yang, Ying Song, Zhengping Feng, Zhihong Wang, Qingfeng Cheng, Linqiang Ma, Yi Yang, Li Zhong, Zhipeng Du, Yue Wang, Ting Luo, Wenwen He, Yue Sun, Fajin Lv, Qifu Li, Shumin Yang Annals of Internal Medicine.2022; 175(10): 1383. CrossRef